The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes the official @localheroai/cli package from the NPM registry. This is a standard vendor-provided resource used to interact with the Localhero.ai platform.
[COMMAND_EXECUTION]: Executes commands via the @localheroai/cli such as translate, glossary, and settings. These operations are used to automate translation management and retrieve project context.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it reads external data to perform its primary function.
Ingestion points: Reads project configuration from localhero.json and content from existing translation files (e.g., JSON, YAML, PO).
Boundary markers: Not present; the agent is instructed to follow existing naming conventions and style found in the source files.
Capability inventory: The skill can execute CLI commands (performing network and file operations) and modify local source files.
Sanitization: No explicit sanitization is performed on the ingested translation data.
[SAFE]: No hardcoded credentials, obfuscated code, or unauthorized persistence mechanisms were detected. The skill follows recommended practices for managing API keys and environment variables.

localhero